Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2640 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.5113. Min Act: -0.0000

Data Index: 464904 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.6337. Min Act: -0.0000

Data Index: 1199173 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.6024. Min Act: -0.0000

Data Index: 306212 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.5614. Min Act: -0.0000

Data Index: 2308 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.6871. Min Act: -0.0000

Data Index: 58234 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.5115. Min Act: -0.0000

Data Index: 727224 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.6012. Min Act: -0.0000

Data Index: 423355 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.4487. Min Act: -0.0000

Data Index: 986644 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.4519. Min Act: -0.0000

Data Index: 675490 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3948. Min Act: -0.0000

Data Index: 559034 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3914. Min Act: -0.0000

Data Index: 137476 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3839. Min Act: -0.0000

Data Index: 1288446 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3956. Min Act: -0.0000

Data Index: 74216 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3882. Min Act: -0.0000

Data Index: 678520 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1291777 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3231. Min Act: -0.0000

Data Index: 864638 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3223. Min Act: -0.0000

Data Index: 1223659 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.2947. Min Act: -0.0000

Data Index: 69481 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.3093. Min Act: -0.0000

Data Index: 118000 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.6871. Min Range: -2.6871

Max Act: 2.2916. Min Act: -0.0000

Data Index: 386408 (C4 (Web Text))

Max Activating Token Index: 570